Kimi-Dev-72B
General purpose
A fine-tune of Qwen2.5 for agentic software tasks. The success of tools like Cursor or Claude Code shows the need for such models. For an analysis of SWE-bench Verified, the benchmark most of these models are evaluated on, see my (Florian's) analysis.
Specs
Params72B
LicenseMIT
Tags
Similarity · VAIL
VAIL Fingerprint
00be:00fb:0144:0221:02a6:039a:0657:49a9
Explore other models with behavioral similarity to Kimi-Dev-72B.
Adoption · Hugging Face
RAM score
Relative Adoption Metric not scored because required parameter, download, or API metadata is not cataloged. This is not a zero score.
Hugging Face Downloads
3K
last 30d
71.8K
all time
HF Likes
392
Relative Adoption Metric not scored because required parameter, download, or API metadata is not cataloged. This is not a zero score.
Related Models
